Model catalog
Models and list rates
Published API prices, in US dollars per million tokens, so you can compare models. tokenstat does not charge these rates. Your subscription bill is separate. The table also shows who lists each model, and whether it can do tools, vision, or reasoning. Recommended order puts known labs first, then newer releases. Free and $0 rows stay hidden unless you ask. Measure real sessions with the app or the CLI.
Showing 48 of 2,422 matches · page 46 of 51 · 97 beta/latest variants hidden (show them) · including free and $0 prices
| Model | Input | Output | Context | Offers |
|---|---|---|---|---|
Gpt Audio Mini 2025 12 15gpt-audio-mini-2025-12-15 | $0.6LiteLLM | $2.40 | N/A | 1 |
Gpt Image 1.5 2025 12 16gpt-image-1.5-2025-12-16 | $5LiteLLM | $10 | N/A | 1 |
Gpt Oss:120b Cloudollama/gpt-oss:120b-cloud | $0LiteLLM | $0 | N/A | 2 |
Gpt Oss:20b Cloudollama/gpt-oss:20b-cloud | $0LiteLLM | $0 | N/A | 2 |
Gpt Realtimegpt-realtime | $4LiteLLM | $16 | N/A | 1 |
Gpt Realtime 1.5 2026 02 23azure/gpt-realtime-1.5-2026-02-23 | $4LiteLLM | $16 | N/A | 2 |
Gpt Realtime 2.1 Miniazure/gpt-realtime-2.1-mini | $0.6LiteLLM | $2.40 | N/A | 2 |
Gpt Realtime 2025 08 28azure/gpt-realtime-2025-08-28 | $4LiteLLM | $16 | N/A | 2 |
Gpt Realtime Mini 2025 10 06azure/gpt-realtime-mini-2025-10-06 | $0.6LiteLLM | $2.40 | N/A | 2 |
Gpt Realtime Mini 2025 12 15gpt-realtime-mini-2025-12-15 | $0.6LiteLLM | $2.40 | N/A | 1 |
Gpt Rosalind Researchgpt-rosalind-research | $5LiteLLM | $25 | N/A | 1 |
Granite 13b Chat V2ibm/granite-13b-chat-v2 | $0.6LiteLLM | $0.6 | N/A | 3 |
Granite 13b Instruct V2ibm/granite-13b-instruct-v2 | $0.6LiteLLM | $0.6 | N/A | 3 |
Granite Guardian 3 2 2bibm/granite-guardian-3-2-2b | $0.1LiteLLM | $0.1 | N/A | 3 |
Granite Ttm 1024 96 R2ibm/granite-ttm-1024-96-r2 | $0.38LiteLLM | $0.38 | N/A | 3 |
Granite Ttm 1536 96 R2ibm/granite-ttm-1536-96-r2 | $0.38LiteLLM | $0.38 | N/A | 3 |
Granite Ttm 512 96 R2ibm/granite-ttm-512-96-r2 | $0.38LiteLLM | $0.38 | N/A | 3 |
Granite Vision 3 2 2bibm/granite-vision-3-2-2b | $0.1LiteLLM | $0.1 | N/A | 3 |
Hermes 4 70Bnebius/NousResearch/Hermes-4-70B | $0.13LiteLLM | $0.4 | N/A | 3 |
Hermes3 405blambda_ai/hermes3-405b | $0.8LiteLLM | $0.8 | N/A | 2 |
Hermes3 70blambda_ai/hermes3-70b | $0.12LiteLLM | $0.3 | N/A | 2 |
Inkling:Batchopenrouter/thinkingmachines/inkling:batch | $1LiteLLM | $4.05 | N/A | 3 |
Internlm2_5 20b Chatollama/internlm2_5-20b-chat | $0LiteLLM | $0 | N/A | 2 |
J2 Lightj2-light | $3LiteLLM | $3 | N/A | 1 |
J2 Midj2-mid | $10LiteLLM | $10 | N/A | 1 |
J2 Ultraj2-ultra | $15LiteLLM | $15 | N/A | 1 |
Jais 13b Chatcore42/jais-13b-chat | $500LiteLLM | $2000 | N/A | 3 |
Jais 30b Chatazure_ai/jais-30b-chat | $3200LiteLLM | $9710 | N/A | 2 |
Jamba 1.5vertex_ai/jamba-1.5 | $0.2LiteLLM | $0.4 | N/A | 2 |
Jamba 1.5 Largevertex_ai/jamba-1.5-large | $2LiteLLM | $8 | N/A | 2 |
Jamba 1.5 Large@001vertex_ai/jamba-1.5-large@001 | $2LiteLLM | $8 | N/A | 2 |
Jamba 1.5 Minivertex_ai/jamba-1.5-mini | $0.2LiteLLM | $0.4 | N/A | 2 |
Jamba 1.5 Mini@001vertex_ai/jamba-1.5-mini@001 | $0.2LiteLLM | $0.4 | N/A | 2 |
Jamba Instructazure_ai/jamba-instruct | $0.5LiteLLM | $0.7 | N/A | 2 |
Jamba Large 1.6jamba-large-1.6 | $2LiteLLM | $8 | N/A | 1 |
Jamba Large 1.7jamba-large-1.7 | $2LiteLLM | $8 | N/A | 1 |
Jamba Mini 1.6jamba-mini-1.6 | $0.2LiteLLM | $0.4 | N/A | 1 |
Jamba Mini 1.7jamba-mini-1.7 | $0.2LiteLLM | $0.4 | N/A | 1 |
Jev 1.13.0typesafe/jev-1.13.0 | $0.042LiteLLM | $0 | N/A | 2 |
Jev Previewtypesafe/jev-preview | $0.042LiteLLM | $0 | N/A | 2 |
Jina Reranker V2 Base Multilingualjina-reranker-v2-base-multilingual | $0.05LiteLLM | $0 | N/A | 1 |
K EXAONE 2.0 750B A37BLGAI-EXAONE/K-EXAONE-2.0-750B-A37B | $0.6LiteLLM | $2.40 | N/A | 3 |
Lfm 40blambda_ai/lfm-40b | $0.1LiteLLM | $0.2 | N/A | 2 |
Ling 3.0 Flash Fastnovita/inclusionai/ling-3.0-flash-fast | $0.06LiteLLM | $0.18 | N/A | 3 |
Llama2ollama/llama2 | $0LiteLLM | $0 | N/A | 2 |
Llama2 13b Chat V1llama2-13b-chat-v1 | $0.75LiteLLM | $1 | N/A | 2 |
Llama2 70b Chat V1llama2-70b-chat-v1 | $1.95LiteLLM | $2.56 | N/A | 2 |
Llama2 Uncensoredollama/llama2-uncensored | $0LiteLLM | $0 | N/A | 2 |
See these prices on your own sessions
tokenstat reads the logs your coding tools already write and prices the tokens at the published API rate. Work your subscription already covered is not an extra bill.