Models & Providers
Tracker runs any model through one of three backends, prices
every run against a shared catalog, and lets you route traffic straight to a
provider or through a gateway. The model list and prices below are
derived from dippin-lang
(the pinned version) — a single source of truth, so what you see here is
exactly what the engine uses to estimate cost and enforce --max-cost.
Backends
Every agent node runs on one backend; you can mix them per node.
| Backend | What it is | Auth |
|---|
native (default) | Tracker’s own turn loop — Anthropic, OpenAI, Google Gemini, and any OpenAI-compatible endpoint. Tool calls, streaming, context compaction, and the writable_paths jail all live here. | Provider API keys (below) |
claude-code | Spawns the claude CLI as a subprocess. Tracker’s five provider keys and their base URLs are stripped so it uses your Max/Pro subscription auth; other credentials pass through. TRACKER_CLAUDE_BIN pins which claude runs. Its reported cost is notional on a subscription, so a claude-code-only run reads ~$X.XX usage (included in your Claude plan). | Subscription (OAuth) |
auto (node value) | Resolved once per run: claude-code when the claude CLI is installed and answers, otherwise native. Announced, recorded in the checkpoint and reused on resume. The explain and quickfix starters use it. | Subscription, else provider key |
acp | ACP-protocol client for headless external agents (claude-agent-acp / codex-acp / gemini --acp). | Per-agent |
Full backend internals: Architecture.
Native providers & keys
The native backend speaks four provider APIs directly. Set the
matching environment variable (or configure it with tracker setup);
tracker doctor verifies them.
| Provider | Key env var | Base-URL override |
|---|
| Anthropic | ANTHROPIC_API_KEY | ANTHROPIC_BASE_URL |
| OpenAI | OPENAI_API_KEY | OPENAI_BASE_URL |
| Google (Gemini) | GEMINI_API_KEY | GEMINI_BASE_URL |
| OpenAI-compatible | OPENAI_API_KEY (or provider’s) | <PROVIDER>_BASE_URL |
OpenAI-compatible is how you reach the other providers in the
catalog below (DeepSeek, Mistral, xAI/Grok, Z.AI, MiniMax, Moonshot, …):
point a *_BASE_URL at their OpenAI-compatible endpoint. A per-provider
<PROVIDER>_BASE_URL always wins over the gateway. These base URLs and the gateway route the native backend only: --backend claude-code launches claude without the provider *_BASE_URLs, and claude never reads TRACKER_GATEWAY_URL. To send claude through a gateway on purpose, export ANTHROPIC_BASE_URL and set TRACKER_PASS_API_KEYS=1.
OpenAI on a ChatGPT subscription v0.80.0: in place of
OPENAI_API_KEY, tracker setup can sign provider: openai nodes in to your own
ChatGPT plan (OpenAI → Auth → ChatGPT subscription, a device code you approve on your phone)
and writes TRACKER_OPENAI_AUTH=chatgpt. From then on OPENAI_BASE_URL and the gateway
don’t apply to openai, usage counts as $0 so dollar ceilings never see it, and the plan’s usage limit
pauses the run for tracker -r. It is for one person’s account on their own machine; see
tracker setup on the CLI page.
Gateway routing
Instead of talking to each provider directly, you can route everything through a
single gateway — a Cloudflare AI Gateway or the 2389 Bedrock proxy — by
setting one URL. Tracker appends a per-provider suffix and otherwise passes the
provider’s API/SSE through unchanged, so a gateway is transparent.
| Setting | Meaning |
|---|
TRACKER_GATEWAY_URL | Base URL of the gateway. When set, providers route through it. |
TRACKER_GATEWAY_KIND | cf-aig (default) or bedrock. Controls the per-provider suffix and routing rules. |
cf-aig appends /anthropic, /openai,
/google-ai-studio, or /compat per provider.
bedrock routes Claude models to Amazon Bedrock (OpenAI/Gemini get
a /v1 suffix; openai-compat is refused). Precedence: a
provider *_BASE_URL beats the gateway. Setup + caveats:
Architecture.
Supported models & prices
Every model dippin-lang
prices, grouped by provider. Prices are US dollars per million tokens.
Cached read is the discounted rate for a prompt-cache hit.
Retired (first-party) means the model 404s on its first-party API but is
still billable through a Bedrock/Vertex passthrough.
Tracker natively adapts Anthropic, OpenAI, and Gemini; the rest are reachable via
an OpenAI-compatible base URL or a gateway. This table is generated from the pinned
dippin version — it can never drift from what the engine bills.
Anthropic
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
claude-fable-5 | $10.00 | $50.00 | $1.00 | — |
claude-fable-5-1 | $10.00 | $50.00 | $0.250 | — |
claude-haiku-3-5 | $0.800 | $4.00 | $0.080 | retired (first-party) |
claude-haiku-4-5 | $1.00 | $5.00 | $0.100 | — |
claude-haiku-5-5 | $0.100 | $0.500 | $0.010 | — |
claude-mythos-5 | $10.00 | $50.00 | $1.00 | — |
claude-mythos-5-1 | $10.00 | $50.00 | $0.250 | — |
claude-opus-4-0 | $15.00 | $75.00 | $1.50 | retired (first-party) |
claude-opus-4-1 | $15.00 | $75.00 | $1.50 | retired (first-party) |
claude-opus-4-5 | $5.00 | $25.00 | $0.500 | — |
claude-opus-4-6 | $5.00 | $25.00 | $0.500 | — |
claude-opus-4-7 | $5.00 | $25.00 | $0.500 | — |
claude-opus-4-8 | $5.00 | $25.00 | $0.500 | — |
claude-opus-5 | $5.00 | $25.00 | $0.500 | — |
claude-opus-5-5 | $4.00 | $20.00 | $0.200 | — |
claude-sonnet-4-0 | $3.00 | $15.00 | $0.300 | retired (first-party) |
claude-sonnet-4-5 | $3.00 | $15.00 | $0.300 | — |
claude-sonnet-4-6 | $3.00 | $15.00 | $0.300 | — |
claude-sonnet-5 | $2.00 | $10.00 | $0.200 | — |
claude-sonnet-5-5 | $2.00 | $10.00 | $0.100 | — |
OpenAI
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
chat-latest | $5.00 | $30.00 | $0.500 | — |
gpt-4.1 | $2.00 | $8.00 | $0.500 | — |
gpt-4.1-mini | $0.400 | $1.60 | $0.100 | — |
gpt-4.1-nano | $0.100 | $0.400 | $0.025 | — |
gpt-4o | $2.50 | $10.00 | $1.25 | — |
gpt-4o-mini | $0.150 | $0.600 | $0.075 | — |
gpt-5 | $1.25 | $10.00 | $0.125 | — |
gpt-5-mini | $0.250 | $2.00 | $0.025 | — |
gpt-5-nano | $0.050 | $0.400 | $0.005 | — |
gpt-5-pro | $15.00 | $120.00 | $15.00 | — |
gpt-5.1 | $1.25 | $10.00 | $0.125 | — |
gpt-5.2 | $1.75 | $14.00 | $0.175 | — |
gpt-5.2-codex | $1.75 | $14.00 | $0.175 | retired (first-party) |
gpt-5.2-pro | $21.00 | $168.00 | $21.00 | — |
gpt-5.3-codex | $1.75 | $14.00 | $0.175 | — |
gpt-5.4 | $2.50 | $15.00 | $0.250 | — |
gpt-5.4-mini | $0.750 | $4.50 | $0.075 | — |
gpt-5.4-nano | $0.200 | $1.25 | $0.020 | — |
gpt-5.4-pro | $30.00 | $180.00 | $30.00 | — |
gpt-5.5 | $5.00 | $30.00 | $0.500 | — |
gpt-5.5-pro | $30.00 | $180.00 | $30.00 | — |
gpt-5.6 | $4.00 | $20.00 | $0.400 | — |
gpt-5.6-luna | $0.200 | $1.20 | $0.020 | — |
gpt-5.6-sol | $4.00 | $20.00 | $0.400 | — |
gpt-5.6-terra | $2.00 | $12.00 | $0.200 | — |
gpt-6-astra | $10.00 | $50.00 | $1.00 | — |
gpt-6-luna | $0.100 | $0.500 | $0.010 | — |
gpt-6-sol | $2.00 | $10.00 | $0.200 | — |
gpt-6.1-sol | $2.00 | $10.00 | $0.100 | — |
o3 | $2.00 | $8.00 | $0.500 | — |
o3-mini | $1.10 | $4.40 | $0.550 | — |
o3-pro | $20.00 | $80.00 | $20.00 | — |
o4-mini | $1.10 | $4.40 | $0.275 | — |
Google (Gemini)
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
gemini-2.0-flash | $0.100 | $0.400 | $0.010 | retired (first-party) |
gemini-2.5-flash | $0.300 | $2.50 | $0.030 | — |
gemini-2.5-flash-lite | $0.100 | $0.400 | $0.010 | — |
gemini-2.5-pro | $1.25 | $10.00 | $0.125 | — |
gemini-3-flash-preview | $0.500 | $3.00 | $0.050 | — |
gemini-3.1-flash-lite | $0.250 | $1.50 | $0.025 | — |
gemini-3.1-flash-lite-preview | $0.250 | $1.50 | $0.025 | retired (first-party) |
gemini-3.1-pro-preview | $2.00 | $12.00 | $0.200 | — |
gemini-3.1-pro-preview-customtools | $2.00 | $12.00 | $0.200 | — |
gemini-3.5-flash | $1.50 | $9.00 | $0.150 | retired (first-party) |
gemini-3.5-flash-lite | $0.300 | $2.50 | $0.030 | — |
gemini-3.6-flash | $1.50 | $7.50 | $0.150 | — |
gemini-3.7-flash | $1.50 | $7.50 | $0.150 | retired (first-party) |
gemini-3.8-flash | $1.50 | $7.50 | $0.150 | — |
gemini-4-argon | $4.00 | $20.00 | $0.200 | — |
gemini-robotics-er-2-preview | $2.00 | $10.00 | $0.200 | — |
DeepSeek
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
deepseek-chat | $0.300 | $1.20 | $0.006 | retired (first-party) |
deepseek-flash | $0.300 | $1.20 | $0.006 | — |
deepseek-reasoner | $0.300 | $1.20 | $0.006 | retired (first-party) |
deepseek-v4-flash | $0.300 | $1.20 | $0.006 | retired (first-party) |
deepseek-v4-pro | $1.32 | $3.96 | $0.044 | — |
deepseek-v4-pro-0813 | $1.32 | $3.96 | $0.044 | — |
xAI (Grok)
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
grok-4-1-fast-non-reasoning | $1.25 | $2.50 | — | retired (first-party) |
grok-4-1-fast-reasoning | $1.25 | $2.50 | — | retired (first-party) |
grok-4.20 | $1.25 | $2.50 | $0.200 | — |
grok-4.20-0309 | $1.25 | $2.50 | $0.200 | — |
grok-4.20-0309-non-reasoning | $1.25 | $2.50 | $0.200 | — |
grok-4.20-0309-reasoning | $1.25 | $2.50 | $0.200 | — |
grok-4.20-multi-agent | $1.25 | $2.50 | $0.200 | — |
grok-4.20-multi-agent-0309 | $1.25 | $2.50 | $0.200 | — |
grok-4.20-multi-agent-latest | $1.25 | $2.50 | $0.200 | — |
grok-4.20-non-reasoning | $1.25 | $2.50 | $0.200 | — |
grok-4.20-non-reasoning-latest | $1.25 | $2.50 | $0.200 | — |
grok-4.20-reasoning | $1.25 | $2.50 | $0.200 | — |
grok-4.20-reasoning-latest | $1.25 | $2.50 | $0.200 | — |
grok-4.3 | $1.25 | $2.50 | $0.200 | — |
grok-4.3-latest | $1.25 | $2.50 | $0.200 | — |
grok-4.5 | $2.00 | $6.00 | $0.300 | — |
grok-4.5-latest | $2.00 | $6.00 | $0.300 | — |
grok-4.6 | $2.00 | $6.00 | $0.500 | — |
grok-4.7 | $2.00 | $6.00 | $0.500 | — |
grok-build-0.1 | $1.00 | $2.00 | $0.200 | — |
grok-build-latest | $2.00 | $6.00 | $0.300 | — |
grok-code-fast | $1.00 | $2.00 | $0.200 | retired (first-party) |
grok-code-fast-1 | $1.00 | $2.00 | $0.200 | retired (first-party) |
grok-code-fast-1-0825 | $1.00 | $2.00 | $0.200 | retired (first-party) |
Mistral
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
codestral | $0.300 | $0.900 | $0.030 | — |
codestral-2508 | $0.300 | $0.900 | $0.030 | — |
codestral-latest | $0.300 | $0.900 | $0.030 | — |
magistral-medium | $2.00 | $5.00 | $0.200 | retired (first-party) |
ministral-14b-2512 | $0.200 | $0.200 | $0.020 | — |
ministral-14b-latest | $0.200 | $0.200 | $0.020 | — |
ministral-3-14b-2512 | $0.200 | $0.200 | $0.020 | — |
ministral-3-3b-2512 | $0.100 | $0.100 | $0.010 | — |
ministral-3-8b-2512 | $0.150 | $0.150 | $0.015 | — |
ministral-3b-2512 | $0.100 | $0.100 | $0.010 | — |
ministral-3b-latest | $0.100 | $0.100 | $0.010 | — |
ministral-8b | $0.100 | $0.100 | $0.100 | retired (first-party) |
ministral-8b-2512 | $0.150 | $0.150 | $0.015 | — |
ministral-8b-latest | $0.150 | $0.150 | $0.015 | — |
mistral-large-2512 | $0.500 | $1.50 | $0.050 | — |
mistral-large-3 | $0.500 | $1.50 | $0.050 | — |
mistral-large-4 | $1.36 | $4.18 | $0.140 | — |
mistral-large-4-0 | $1.36 | $4.18 | $0.140 | — |
mistral-large-latest | $0.500 | $1.50 | $0.050 | — |
mistral-medium-3 | $1.50 | $7.50 | $0.150 | — |
mistral-medium-3-1-2508 | $0.400 | $2.00 | $0.400 | retired (first-party) |
mistral-medium-3-5 | $1.50 | $7.50 | $0.150 | — |
mistral-medium-3-5-2604 | $1.50 | $7.50 | $0.150 | — |
mistral-medium-latest | $1.50 | $7.50 | $0.150 | — |
mistral-nemo | $0.150 | $0.150 | $0.150 | retired (first-party) |
mistral-small | $0.150 | $0.600 | $0.015 | — |
mistral-small-2603 | $0.150 | $0.600 | $0.015 | — |
mistral-small-latest | $0.150 | $0.600 | $0.015 | — |
Cohere
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
c4ai-aya-expanse-32b | $0.500 | $1.50 | $0.500 | — |
command-r | $0.500 | $1.50 | $0.500 | retired (first-party) |
command-r-08-2024 | $0.150 | $0.600 | $0.150 | — |
command-r-plus | $3.00 | $15.00 | $3.00 | retired (first-party) |
command-r-plus-08-2024 | $2.50 | $10.00 | $2.50 | — |
command-r7b | $0.037 | $0.150 | $0.037 | — |
command-r7b-12-2024 | $0.037 | $0.150 | $0.037 | — |
Z.AI (GLM)
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
glm-4-32b-0414-128k | $0.100 | $0.100 | — | — |
glm-4.5 | $0.600 | $2.20 | $0.110 | — |
glm-4.5-air | $0.200 | $1.10 | $0.030 | — |
glm-4.5-airx | $1.10 | $4.50 | $0.220 | — |
glm-4.5-x | $2.20 | $8.90 | $0.450 | — |
glm-4.5v | $0.600 | $1.80 | $0.110 | — |
glm-4.6 | $0.600 | $2.20 | $0.110 | — |
glm-4.6v | $0.300 | $0.900 | $0.050 | — |
glm-4.6v-flashx | $0.040 | $0.400 | $0.004 | — |
glm-4.7 | $0.600 | $2.20 | $0.110 | — |
glm-4.7-flashx | $0.070 | $0.400 | $0.010 | — |
glm-5 | $1.00 | $3.20 | $0.200 | — |
glm-5.1 | $1.40 | $4.40 | $0.260 | — |
glm-5.2 | $1.40 | $4.40 | $0.260 | — |
glm-5.3 | $1.40 | $4.40 | $0.260 | — |
glm-5.3-flash | $0.150 | $0.500 | $0.030 | — |
glm-5.3-flashx | $0.370 | $1.25 | $0.075 | — |
MiniMax
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
MiniMax-M2 | $0.300 | $1.20 | — | retired (first-party) |
MiniMax-M2.1 | $0.300 | $1.20 | — | retired (first-party) |
MiniMax-M2.5 | $0.300 | $1.20 | — | — |
MiniMax-M2.5-highspeed | $0.600 | $2.40 | — | — |
MiniMax-M2.7 | $0.300 | $1.20 | — | — |
MiniMax-M2.7-highspeed | $0.600 | $2.40 | — | — |
MiniMax-M3 | $0.300 | $1.20 | $0.060 | — |
MiniMax-M3.1-Flash | $0.150 | $0.600 | $0.015 | — |
Moonshot (Kimi)
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
kimi-k2.6 | $0.950 | $4.00 | $0.160 | — |
kimi-k2.7-code | $0.950 | $4.00 | $0.190 | — |
kimi-k2.7-code-highspeed | $1.90 | $8.00 | $0.380 | — |
kimi-k3 | $3.00 | $15.00 | $0.300 | — |
kimi-k3.1-pro | $2.00 | $10.00 | $0.200 | — |
kimi-k3.1-pro-highspeed | $4.00 | $20.00 | $0.200 | — |
Qwen
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
qwen3.6-flash | $0.250 | $1.50 | $0.025 | — |
qwen3.6-plus | $0.500 | $3.00 | $0.050 | — |
qwen3.7-flash | $0.030 | $0.130 | $0.006 | — |
qwen3.7-max | $2.50 | $7.50 | $0.500 | — |
qwen3.7-max-preview | $2.50 | $7.50 | $2.50 | — |
qwen3.7-plus | $0.400 | $1.60 | $0.080 | — |
qwen3.8-flash | $0.150 | $0.470 | — | — |
qwen3.8-max | $2.00 | $6.00 | — | — |
qwen3.8-max-0902 | $2.00 | $6.00 | — | — |
| Model | Input /M | Output /M | Cached read /M | Notes |
|---|
muse-spark-1.1 | $1.25 | $4.25 | $0.150 | — |
muse-spark-1.2 | $1.25 | $4.25 | $0.150 | — |
muse-spark-1.2-contributor | $0.100 | $0.200 | $0.002 | — |
muse-spark-1.3 | $1.25 | $4.25 | $0.150 | — |
muse-spark-1.3-contributor | $0.100 | $0.200 | $0.002 | — |
muse-wonder-1.0 | $4.00 | $20.00 | $0.200 | — |
Cost governance
Because every model above carries a price, Tracker estimates the dollar cost of a
run and enforces hard ceilings between nodes. Breach any cap and the run halts with
a cost snapshot you can resume.
tracker --max-cost 500 --max-tokens 100000 --max-wall-time 30m build_product
--max-cost is in cents. A model dippin doesn’t price runs at $0
(with a one-time warning), so a ceiling can’t silently fail to apply. The catalog holds one price per model, so prompts above a provider’s long-context threshold (Haiku 5.5 above 100K tokens, GPT-6 above 272K) bill higher than the estimate — leave headroom on long-context runs. Full
budget model: CLI Reference.